October 15, 2019

2669 words 13 mins read

Paper Group NANR 185

Si O No, Que Penses? Catalonian Independence and Linguistic Identity on Social Media. Equivalence of Multicategory SVM and Simplex Cone SVM: Fast Computations and Statistical Theory. Learning Priors for Semantic 3D Reconstruction. ExtRA: Extracting Prominent Review Aspects from Customer Feedback. Weighted DAG Automata for Semantic Graphs. Addressin …


Title	Si O No, Que Penses? Catalonian Independence and Linguistic Identity on Social Media
Authors	Ian Stewart, Yuval Pinter, Jacob Eisenstein
Abstract	Political identity is often manifested in language variation, but the relationship between the two is still relatively unexplored from a quantitative perspective. This study examines the use of Catalan, a language local to the semi-autonomous region of Catalonia in Spain, on Twitter in discourse related to the 2017 independence referendum. We corroborate prior findings that pro-independence tweets are more likely to include the local language than anti-independence tweets. We also find that Catalan is used more often in referendum-related discourse than in other contexts, contrary to prior findings on language variation. This suggests a strong role for the Catalan language in the expression of Catalonian political identity.
Tasks
Published	2018-06-01
URL	https://www.aclweb.org/anthology/N18-2022/
PDF	https://www.aclweb.org/anthology/N18-2022
PWC	https://paperswithcode.com/paper/si-o-no-que-penses-catalonian-independence
Repo
Framework

Equivalence of Multicategory SVM and Simplex Cone SVM: Fast Computations and Statistical Theory


Title	Equivalence of Multicategory SVM and Simplex Cone SVM: Fast Computations and Statistical Theory
Authors	Guillaume Pouliot
Abstract	The multicategory SVM (MSVM) of Lee et al. (2004) is a natural generalization of the classical, binary support vector machines (SVM). However, its use has been limited by computational difficulties. The simplex-cone SVM (SCSVM) of Mroueh et al. (2012) is a computationally efficient multicategory classifier, but its use has been limited by a seemingly opaque interpretation. We show that MSVM and SCSVM are in fact exactly equivalent, and provide a bijection between their tuning parameters. MSVM may then be entertained as both a natural and computationally efficient multicategory extension of SVM. We further provide a Donsker theorem for finite-dimensional kernel MSVM and partially answer the open question pertaining to the very competitive performance of One-vs-Rest methods against MSVM. Furthermore, we use the derived asymptotic covariance formula to develop an inverse-variance weighted classification rule which improves on the One-vs-Rest approach.
Tasks
Published	2018-07-01
URL	https://icml.cc/Conferences/2018/Schedule?showEvent=2427
PDF	http://proceedings.mlr.press/v80/pouliot18a/pouliot18a.pdf
PWC	https://paperswithcode.com/paper/equivalence-of-multicategory-svm-and-simplex
Repo
Framework

Learning Priors for Semantic 3D Reconstruction


Title	Learning Priors for Semantic 3D Reconstruction
Authors	Ian Cherabier, Johannes L. Schonberger, Martin R. Oswald, Marc Pollefeys, Andreas Geiger
Abstract	We present a novel semantic 3D reconstruction framework which embeds variational regularization into a neural network. Our network performs a fixed number of unrolled multi-scale optimization iterations with shared interaction weights. In contrast to existing variational methods for semantic 3D reconstruction, our model is end-to-end trainable and captures more complex dependencies between the semantic labels and the 3D geometry. Compared to previous learning-based approaches to 3D reconstruction, we integrate powerful long-range dependencies using variational coarse-to-fine optimization. As a result, our network architecture requires only a moderate number of parameters while keeping a high level of expressiveness which enables learning from very little data. Experiments on real and synthetic datasets demonstrate that our network achieves higher accuracy compared to a purely variational approach while at the same time requiring two orders of magnitude less iterations to converge. Moreover, our approach handles ten times more semantic class labels using the same computational resources.
Tasks	3D Reconstruction
Published	2018-09-01
URL	http://openaccess.thecvf.com/content_ECCV_2018/html/Ian_Cherabier_Learning_Priors_for_ECCV_2018_paper.html
PDF	http://openaccess.thecvf.com/content_ECCV_2018/papers/Ian_Cherabier_Learning_Priors_for_ECCV_2018_paper.pdf
PWC	https://paperswithcode.com/paper/learning-priors-for-semantic-3d
Repo
Framework

ExtRA: Extracting Prominent Review Aspects from Customer Feedback


Title	ExtRA: Extracting Prominent Review Aspects from Customer Feedback
Authors	Zhiyi Luo, Shanshan Huang, Frank F. Xu, Bill Yuchen Lin, Hanyuan Shi, Kenny Zhu
Abstract	Many existing systems for analyzing and summarizing customer reviews about products or service are based on a number of prominent review aspects. Conventionally, the prominent review aspects of a product type are determined manually. This costly approach cannot scale to large and cross-domain services such as Amazon.com, Taobao.com or Yelp.com where there are a large number of product types and new products emerge almost every day. In this paper, we propose a novel framework, for extracting the most prominent aspects of a given product type from textual reviews. The proposed framework, ExtRA, extracts K most prominent aspect terms or phrases which do not overlap semantically automatically without supervision. Extensive experiments show that ExtRA is effective and achieves the state-of-the-art performance on a dataset consisting of different product types.
Tasks
Published	2018-10-01
URL	https://www.aclweb.org/anthology/D18-1384/
PDF	https://www.aclweb.org/anthology/D18-1384
PWC	https://paperswithcode.com/paper/extra-extracting-prominent-review-aspects
Repo
Framework

Weighted DAG Automata for Semantic Graphs


Title	Weighted DAG Automata for Semantic Graphs
Authors	David Chiang, Frank Drewes, Daniel Gildea, Adam Lopez, Giorgio Satta
Abstract	Graphs have a variety of uses in natural language processing, particularly as representations of linguistic meaning. A deficit in this area of research is a formal framework for creating, combining, and using models involving graphs that parallels the frameworks of finite automata for strings and finite tree automata for trees. A possible starting point for such a framework is the formalism of directed acyclic graph (DAG) automata, defined by Kamimura and Slutzki and extended by Quernheim and Knight. In this article, we study the latter in depth, demonstrating several new results, including a practical recognition algorithm that can be used for inference and learning with models defined on DAG automata. We also propose an extension to graphs with unbounded node degree and show that our results carry over to the extended formalism.
Tasks
Published	2018-03-01
URL	https://www.aclweb.org/anthology/J18-1005/
PDF	https://www.aclweb.org/anthology/J18-1005
PWC	https://paperswithcode.com/paper/weighted-dag-automata-for-semantic-graphs
Repo
Framework

Addressing Low-Resource Scenarios with Character-aware Embeddings


Title	Addressing Low-Resource Scenarios with Character-aware Embeddings
Authors	Sean Papay, Sebastian Pad{'o}, Ngoc Thang Vu
Abstract	Most modern approaches to computing word embeddings assume the availability of text corpora with billions of words. In this paper, we explore a setup where only corpora with millions of words are available, and many words in any new text are out of vocabulary. This setup is both of practical interests {–} modeling the situation for specific domains and low-resource languages {–} and of psycholinguistic interest, since it corresponds much more closely to the actual experiences and challenges of human language learning and use. We compare standard skip-gram word embeddings with character-based embeddings on word relatedness prediction. Skip-grams excel on large corpora, while character-based embeddings do well on small corpora generally and rare and complex words specifically. The models can be combined easily.
Tasks	Morphological Analysis, Word Embeddings
Published	2018-06-01
URL	https://www.aclweb.org/anthology/W18-1204/
PDF	https://www.aclweb.org/anthology/W18-1204
PWC	https://paperswithcode.com/paper/addressing-low-resource-scenarios-with
Repo
Framework

Hybrid Neural Attention for Agreement/Disagreement Inference in Online Debates


Title	Hybrid Neural Attention for Agreement/Disagreement Inference in Online Debates
Authors	Di Chen, Jiachen Du, Lidong Bing, Ruifeng Xu
Abstract	Inferring the agreement/disagreement relation in debates, especially in online debates, is one of the fundamental tasks in argumentation mining. The expressions of agreement/disagreement usually rely on argumentative expressions in text as well as interactions between participants in debates. Previous works usually lack the capability of jointly modeling these two factors. To alleviate this problem, this paper proposes a hybrid neural attention model which combines self and cross attention mechanism to locate salient part from textual context and interaction between users. Experimental results on three (dis)agreement inference datasets show that our model outperforms the state-of-the-art models.
Tasks	Natural Language Inference, Sentiment Analysis
Published	2018-10-01
URL	https://www.aclweb.org/anthology/D18-1069/
PDF	https://www.aclweb.org/anthology/D18-1069
PWC	https://paperswithcode.com/paper/hybrid-neural-attention-for
Repo
Framework

Variable Selection via Penalized Neural Network: a Drop-Out-One Loss Approach


Title	Variable Selection via Penalized Neural Network: a Drop-Out-One Loss Approach
Authors	Mao Ye, Yan Sun
Abstract	We propose a variable selection method for high dimensional regression models, which allows for complex, nonlinear, and high-order interactions among variables. The proposed method approximates this complex system using a penalized neural network and selects explanatory variables by measuring their utility in explaining the variance of the response variable. This measurement is based on a novel statistic called Drop-Out-One Loss. The proposed method also allows (overlapping) group variable selection. We prove that the proposed method can select relevant variables and exclude irrelevant variables with probability one as the sample size goes to infinity, which is referred to as the Oracle Property. Experimental results on simulated and real world datasets show the efficiency of our method in terms of variable selection and prediction accuracy.
Tasks
Published	2018-07-01
URL	https://icml.cc/Conferences/2018/Schedule?showEvent=1995
PDF	http://proceedings.mlr.press/v80/ye18b/ye18b.pdf
PWC	https://paperswithcode.com/paper/variable-selection-via-penalized-neural
Repo
Framework

Modelling Natural Language, Programs, and their Intersection


Title	Modelling Natural Language, Programs, and their Intersection
Authors	Graham Neubig, Miltiadis Allamanis
Abstract	As computers and information grow a more integral part of our world, it is becoming more and more important for humans to be able to interact with their computers in complex ways. One way to do so is by programming, but the ability to understand and generate programming languages is a highly specialized skill. As a result, in the past several years there has been an increasing research interest in methods that focus on the intersection of programming and natural language, allowing users to use natural language to interact with computers in the complex ways that programs allow us to do. In this tutorial, we will focus on machine learning models of programs and natural language focused on making this goal a reality. First, we will discuss the similarities and differences between programming and natural language. Then we will discuss methods that have been designed to cover a variety of tasks in this field, including automatic explanation of programs in natural language (code-to-language), automatic generation of programs from natural language specifications (language-to-code), modeling the natural language elements of source code, and analysis of communication in collaborative programming communities. The tutorial will be aimed at NLP researchers and practitioners, aiming to describe the interesting opportunities that models at the intersection of natural and programming languages provide, and also how their techniques could provide benefit to the practice of software engineering as a whole.
Tasks	Semantic Parsing, Text Generation
Published	2018-06-01
URL	https://www.aclweb.org/anthology/N18-6001/
PDF	https://www.aclweb.org/anthology/N18-6001
PWC	https://paperswithcode.com/paper/modelling-natural-language-programs-and-their
Repo
Framework

Monocular 3D Pose and Shape Estimation of Multiple People in Natural Scenes - The Importance of Multiple Scene Constraints


Title	Monocular 3D Pose and Shape Estimation of Multiple People in Natural Scenes - The Importance of Multiple Scene Constraints
Authors	Andrei Zanfir, Elisabeta Marinoiu, Cristian Sminchisescu
Abstract	Human sensing has greatly benefited from recent advances in deep learning, parametric human modeling, and large scale 2d and 3d datasets. However, existing 3d models make strong assumptions about the scene, considering either a single person per image, full views of the person, a simple background or many cameras. In this paper, we leverage state-of-the-art deep multi-task neural networks and parametric human and scene modeling, towards a fully automatic monocular visual sensing system for multiple interacting people, which (i) infers the 2d and 3d pose and shape of multiple people from a single image, relying on detailed semantic representations at both model and image level, to guide a combined optimization with feedforward and feedback components, (ii) automatically integrates scene constraints including ground plane support and simultaneous volume occupancy by multiple people, and (iii) extends the single image model to video by optimally solving the temporal person assignment problem and imposing coherent temporal pose and motion reconstructions while preserving image alignment fidelity. We perform experiments on both single and multi-person datasets, and systematically evaluate each component of the model, showing improved performance and extensive multiple human sensing capability. We also apply our method to images with multiple people, severe occlusions and diverse backgrounds captured in challenging natural scenes, and obtain results of good perceptual quality.
Tasks
Published	2018-06-01
URL	http://openaccess.thecvf.com/content_cvpr_2018/html/Zanfir_Monocular_3D_Pose_CVPR_2018_paper.html
PDF	http://openaccess.thecvf.com/content_cvpr_2018/papers/Zanfir_Monocular_3D_Pose_CVPR_2018_paper.pdf
PWC	https://paperswithcode.com/paper/monocular-3d-pose-and-shape-estimation-of
Repo
Framework

Joint learning of frequency and word embeddings for multilingual readability assessment


Title	Joint learning of frequency and word embeddings for multilingual readability assessment
Authors	Dieu-Thu Le, Cam-Tu Nguyen, Xiaoliang Wang
Abstract	This paper describes two models that employ word frequency embeddings to deal with the problem of readability assessment in multiple languages. The task is to determine the difficulty level of a given document, i.e., how hard it is for a reader to fully comprehend the text. The proposed models show how frequency information can be integrated to improve the readability assessment. The experimental results testing on both English and Chinese datasets show that the proposed models improve the results notably when comparing to those using only traditional word embeddings.
Tasks	Word Embeddings
Published	2018-07-01
URL	https://www.aclweb.org/anthology/W18-3714/
PDF	https://www.aclweb.org/anthology/W18-3714
PWC	https://paperswithcode.com/paper/joint-learning-of-frequency-and-word
Repo
Framework

Learning Representations for Detecting Abusive Language


Title	Learning Representations for Detecting Abusive Language
Authors	Magnus Sahlgren, Tim Isbister, Fredrik Olsson
Abstract	This paper discusses the question whether it is possible to learn a generic representation that is useful for detecting various types of abusive language. The approach is inspired by recent advances in transfer learning and word embeddings, and we learn representations from two different datasets containing various degrees of abusive language. We compare the learned representation with two standard approaches; one based on lexica, and one based on data-specific $n$-grams. Our experiments show that learned representations \textit{do} contain useful information that can be used to improve detection performance when training data is limited.
Tasks	Language Modelling, Representation Learning, Text Classification, Transfer Learning, Word Embeddings
Published	2018-10-01
URL	https://www.aclweb.org/anthology/W18-5115/
PDF	https://www.aclweb.org/anthology/W18-5115
PWC	https://paperswithcode.com/paper/learning-representations-for-detecting
Repo
Framework

Resources to Examine the Quality of Word Embedding Models Trained on n-Gram Data


Title	Resources to Examine the Quality of Word Embedding Models Trained on n-Gram Data
Authors	{'A}bel Elekes, Adrian Englhardt, Martin Sch{"a}ler, Klemens B{"o}hm
Abstract	Word embeddings are powerful tools that facilitate better analysis of natural language. However, their quality highly depends on the resource used for training. There are various approaches relying on n-gram corpora, such as the Google n-gram corpus. However, n-gram corpora only offer a small window into the full text {–} 5 words for the Google corpus at best. This gives way to the concern whether the extracted word semantics are of high quality. In this paper, we address this concern with two contributions. First, we provide a resource containing 120 word-embedding models {–} one of the largest collection of embedding models. Furthermore, the resource contains the n-gramed versions of all used corpora, as well as our scripts used for corpus generation, model generation and evaluation. Second, we define a set of meaningful experiments allowing to evaluate the aforementioned quality differences. We conduct these experiments using our resource to show its usage and significance. The evaluation results confirm that one generally can expect high quality for n-grams with n {\textgreater} 3.
Tasks	Semantic Textual Similarity, Sentiment Analysis, Word Embeddings
Published	2018-10-01
URL	https://www.aclweb.org/anthology/K18-1041/
PDF	https://www.aclweb.org/anthology/K18-1041
PWC	https://paperswithcode.com/paper/resources-to-examine-the-quality-of-word
Repo
Framework

Accurate semantic textual similarity for cleaning noisy parallel corpora using semantic machine translation evaluation metric: The NRC supervised submissions to the Parallel Corpus Filtering task


Title	Accurate semantic textual similarity for cleaning noisy parallel corpora using semantic machine translation evaluation metric: The NRC supervised submissions to the Parallel Corpus Filtering task
Authors	Chi-kiu Lo, Michel Simard, Darlene Stewart, Samuel Larkin, Cyril Goutte, Patrick Littell
Abstract	We present our semantic textual similarity approach in filtering a noisy web crawled parallel corpus using YiSi{—}a novel semantic machine translation evaluation metric. The systems mainly based on this supervised approach perform well in the WMT18 Parallel Corpus Filtering shared task (4th place in 100-million-word evaluation, 8th place in 10-million-word evaluation, and 6th place overall, out of 48 submissions). In fact, our best performing system{—}NRC-yisi-bicov is one of the only four submissions ranked top 10 in both evaluations. Our submitted systems also include some initial filtering steps for scaling down the size of the test corpus and a final redundancy removal step for better semantic and token coverage of the filtered corpus. In this paper, we also describe our unsuccessful attempt in automatically synthesizing a noisy parallel development corpus for tuning the weights to combine different parallelism and fluency features.
Tasks	Machine Translation, Semantic Textual Similarity, Tokenization
Published	2018-10-01
URL	https://www.aclweb.org/anthology/W18-6481/
PDF	https://www.aclweb.org/anthology/W18-6481
PWC	https://paperswithcode.com/paper/accurate-semantic-textual-similarity-for
Repo
Framework

Using Discourse Information for Education with a Spanish-Chinese Parallel Corpus


Title	Using Discourse Information for Education with a Spanish-Chinese Parallel Corpus
Authors	Shuyuan Cao, Harritxu Gete
Abstract
Tasks	Speech Recognition
Published	2018-05-01
URL	https://www.aclweb.org/anthology/L18-1357/
PDF	https://www.aclweb.org/anthology/L18-1357
PWC	https://paperswithcode.com/paper/using-discourse-information-for-education
Repo
Framework